
# import libraries 
import altair as alt
import pandas as pd


# Load the dataset into a Pandas DataFrame
data = pd.read_excel('SFTT.xlsx')


xmin = data['Point X'].min()
xmax = data['Point X'].max()
ymin = data['Point Y'].min()
ymax = data['Point Y'].max()

ratio = (xmax - xmin) / (ymax - ymin)

height = 400
geoscalar = 1.2 # Amount to scale the size of the geographical distribution
width = height * ratio # Multiply by ratio for equirectangular maps


# Remove white spaces from column names
data = data.rename(columns=lambda x: x.strip())

data = data[data['Tree Present'] == True]
data = data.astype({'Postal Code': 'string'})
data['Postal Code'] = data['Postal Code'].apply(lambda x: '{0:0>7}'.format(x))
data['Postal Code'] = data['Postal Code'].str[:-2]


# Drop rows with missing values in the 'Species' column
if 'Species' in data.columns:
    data = data.dropna(subset=['Species'])


# The color messed with the data type
data = data.rename(columns = {'Tree: Tree Condition': "Tree Condition"})


# Clean our data, take out postal codes that are too far from the Mass Ave Corridor
#data = data[~data['Postal Code'].isin(['02116', '02130', '02136', '00021', '000<N', '02129', '02109', '02113', '02122', '02128', '02201', '02215', '02445', '02124', '02127', '02110', '02108'])]
data = data[~data['Postal Code'].isin(['000<N', '02136', '02129', '02445'])]

postal_codes = data['Postal Code'].unique()


options = ['02115', '02120', '02119', '02118', '02121', '02125']
labels = [option + ' ' for option in options]

input_dropdown = alt.binding_radio(
    # Add the empty selection which shows all when clicked
    options=options + [None],
    labels=labels + ['All'],
    name='Postal Codes: '
)
code_select = alt.selection_point(
    fields=['Postal Code'],
    bind=input_dropdown,
)


# Source: https://altair-viz.github.io/user_guide/marks/geoshape.html
geobounds = alt.Feature(
    type = 'Feature',
    properties = {},
    geometry = alt.Geometry(
        alt.Polygon(
            type = 'Polygon',
            coordinates = [[
                [xmax, ymax],
                [xmax, ymin],
                [xmin, ymin],
                [xmin, ymax],
                [xmax, ymax]
            ]]
        )
    )
)



# The following code is taken from the Altair Tutorial done in class on 5/23/23
zip_code_url = 'https://raw.githubusercontent.com/ethangu8/DS4200/main/ZIP_Codes%20(1).geojson'
zip_codes = alt.topo_feature(zip_code_url, feature='features')

zip_code_map = alt.Chart(zip_codes).mark_geoshape(
    fill = 'lightgray',
    stroke = 'white',
    clip = True
).project(
    type = 'equirectangular',
    fit = geobounds
).properties(
    height = height * geoscalar,
    width = width * geoscalar
)


from collections import Counter
a = Counter(data['Common Name'].tolist()).most_common(10)
names = [i[0] for i in a]
common_names = data[data['Common Name'].isin(names)]

b = Counter(data['Postal Code'].tolist()).most_common(9)
codes = [i[0] for i in b]
common_codes = data[data['Postal Code'].isin(codes)]


data2 = common_codes[common_codes['Common Name'].isin(names)]


b1 = data2[['Point X', 'Point Y', 'Postal Code', 'Species', 'Genus', 'Common Name']]
b1.head(5)


import numpy as np
postal_codes = data2['Postal Code'].unique()
dropdown = alt.binding_select(options = [None] + list(postal_codes), labels = ['All'] + list(postal_codes))
code_select = alt.selection_single(
    fields=["Postal Code"],
    bind=dropdown,
    name="Postal Codes",
)

C:\Users\ethan\anaconda3\lib\site-packages\altair\utils\deprecation.py:65: AltairDeprecationWarning: 'selection_single' is deprecated.  Use 'selection_point'
  warnings.warn(message, AltairDeprecationWarning, stacklevel=1)


brush = alt.selection_interval()
brush1 = alt.selection_interval()

selection = alt.selection_point(fields=['Postal Code'])
trees = alt.Chart(data2).mark_circle(size=30).encode(
    longitude="Point X:Q",
    latitude="Point Y:Q",
    color="Postal Code",
    #size=alt.Size('Diameter:Q', scale=alt.Scale(range=[10, 150])),
    tooltip=["Genus","Common Name", "Postal Code", "Species", "Street Address"]
).add_params(brush, code_select, selection
).transform_filter(code_select). transform_filter(brush1
).properties(title='Trees Across Boston')


# Create an interactive histogram layer to show the count of trees by zip code
trees_by_code = alt.Chart(data2).mark_bar().encode(
    alt.X('count():Q', title='Tree Count'),
    alt.Y('Postal Code:N', title='Zip Code').sort('-x'),
    color = 'Postal Code:N',
    tooltip=['Postal Code', 'count()']
    ).add_params(selection).transform_filter(code_select).transform_filter(brush
).properties(title='Number of Trees by Postal Code')

common_trees = alt.Chart(data2).mark_bar().encode(
    alt.X('count():Q', title='Tree Count'),
    alt.Y('Common Name:N', title='Common Name').sort('-x'),
    color='Postal Code',
    tooltip=['Postal Code', 'count()']
    ).add_params(brush1).transform_filter(code_select
).transform_filter(brush).properties(title='Most Common Trees')


#trees & histogram | common_trees

zip_code_map + trees | trees_by_code & common_trees
#trees


chart = alt.vconcat(zip_code_map + trees | trees_by_code & common_trees)
chart.save('Final_Viz.html')

	Point X	Point Y	Postal Code	Species	Genus	Common Name
1	-71.101275	42.339655	02115	cordata	Tilia	Littleleaf linden
2	-71.091306	42.337096	02115	acerifolia	Platanus	London planetree
3	-71.091495	42.337111	02115	acerifolia	Platanus	London planetree
4	-71.091278	42.337240	02115	acerifolia	Platanus	London planetree
5	-71.091397	42.337220	02115	acerifolia	Platanus	London planetree

Design¶